机构地区: 广州城市职业学院信息与汽车工程学院
出 处: 《华南师范大学学报(自然科学版)》 2011年第4期63-66,共4页
摘 要: 朴素贝叶斯分类器是机器学习领域中一种重要的分类算法,根据该算法的前提,利用Foley-Sammon变换算法进行特征提取,提出了一种基于Foley-Sammon变换的朴素贝叶斯分类器NBFST(Na ve Bayesian Classifier with Foley-Sammon Transform).结果表明,NBFST能够在大多数数据集上具有较高的分类准确率. As an important classifying method in machine learning,Nave Bayesian classifier is based on the assumption that the attribute values are conditionally independent with given target values.According to this assumption,a Nave Bayesian classifier with Foley-Sammon Transform NBFST is proposed.The NBFST is compared with NB(Nave Bayesian),NBPCA(Nave Bayesian with principle component analysis) and NBFDA(Nave Bayesian with Fisher Discriminant Analysis) by experiments.Experiment results show that NBFST has higher accuracy than other classifying methods in most data sets.
关 键 词: 变换 朴素贝叶斯 特征提取 条件独立 机器学习
领 域: [自动化与计算机技术] [自动化与计算机技术]